© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 61969
    Prev
    Next
    INDEX
    Explanations

    negative affirmations and expressions of uncertainty

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    I don't know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     resourceCulture
    -0.56
     ویکی‌پدی
    -0.46
    esModule
    -0.46
    存于互联网档案馆
    -0.44
     avena
    -0.42
    κτηρισ
    -0.41
    NumberOf
    -0.40
     CanadaChoose
    -0.40
     bicchiere
    -0.40
    로운
    -0.38
    POSITIVE LOGITS
     Idk
    1.38
     idk
    1.37
    Idk
    1.29
    idk
    1.20
     dunno
    1.08
    IDK
    1.06
    Dunno
    0.90
     wtf
    0.75
     tbh
    0.74
    Tbh
    0.73
    Activations Density 0.009%

    No Known Activations